We lifted 12 functions out of this paper's own repositories and ran 9 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| dammsi/AnomalyDINO | canonical | 9 of 12 |
| Function | Status | Where it lives |
|---|---|---|
| augment_image | Ran | dammsi/AnomalyDINO/src/utils.py code served (permissive licence) · get_code("69b7ec756f0c3924") |
| dists2map | Ran | dammsi/AnomalyDINO/src/utils.py code served (permissive licence) · get_code("ea8c5ee4a0cc0f8f") |
| dists_to_score | Ran | dammsi/AnomalyDINO/run_anomalydino_batched.py code served (permissive licence) · get_code("e837264fac14ebc8") |
| get_test_gt_map | Ran | dammsi/AnomalyDINO/src/visualize.py code served (permissive licence) · get_code("7588be1b4b26487d") |
| infer_vmax | Ran | dammsi/AnomalyDINO/src/visualize.py code served (permissive licence) · get_code("c5636a40063ed27f") |
| parse_dataset_files | Ran | dammsi/AnomalyDINO/src/post_eval.py code served (permissive licence) · get_code("74ecf65bc944b930") |
| read_tiff | Ran | dammsi/AnomalyDINO/src/post_eval.py code served (permissive licence) · get_code("4986e9bea3ab5f62") |
| rotate_image | Ran | dammsi/AnomalyDINO/src/utils.py code served (permissive licence) · get_code("c1f46db4781a63e8") |
| trapezoid | Ran | dammsi/AnomalyDINO/src/post_eval.py code served (permissive licence) · get_code("560659bf3ee27551") |
| calculate_cosine_distances | Not yet run | dammsi/AnomalyDINO/run_anomalydino_batched.py code served (permissive licence) · get_code("48b441c02be46c8e") |
| evaluate_ad_batched | Not yet run | dammsi/AnomalyDINO/run_anomalydino_batched.py code served (permissive licence) · get_code("5b94b0890753f50f") |
| get_model | Not yet run | dammsi/AnomalyDINO/src/backbones.py code served (permissive licence) · get_code("c999edb411941138") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent advances in multimodal foundation models have set new standards in few-shot anomaly detection. This paper explores whether high-quality visual features alone are sufficient to rival existing state-of-the-art vision-language models. We affirm this by adapting DINOv2 for one-shot and few-shot anomaly detection, with a focus on industrial applications. We show that this approach does not only rival existing techniques but can even outmatch them in many settings. Our proposed vision-only approach, AnomalyDINO, follows the well-established patch-level deep nearest neighbor paradigm, and enables both image-level anomaly prediction and pixel-level anomaly segmentation. The approach is methodologically simple and training-free and, thus, does not require any additional data for fine-tuning or meta-learning. The approach is methodologically simple and training-free and, thus, does not require any additional data for fine-tuning or meta-learning. Despite its simplicity, AnomalyDINO achieves state-of-the-art results in one- and few-shot anomaly detection (e.g., pushing the one-shot performance on MVTec-AD from an AUROC of 93.1% to 96.6%). The reduced overhead, coupled with its outstanding few-shot performance, makes AnomalyDINO a strong candidate for fast deployment, e.g., in industrial contexts.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2405.14529")
get_code_for_paper("2405.14529")
have("2405.14529")
Connect an agent — have() is free.